Training in progress, step 2000

adapter_config.json

@@ -0,0 +1,123 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "EleutherAI/polyglot-ko-1.3b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gpt_neox.layers.20.attention.dense",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h",
+    "gpt_neox.layers.15.attention.dense",
+    "gpt_neox.layers.5.attention.query_key_value",
+    "gpt_neox.layers.5.attention.dense",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h",
+    "gpt_neox.layers.15.attention.query_key_value",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h",
+    "gpt_neox.layers.0.attention.query_key_value",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h",
+    "gpt_neox.layers.12.attention.dense",
+    "gpt_neox.layers.4.attention.dense",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h",
+    "gpt_neox.layers.20.attention.query_key_value",
+    "gpt_neox.layers.2.attention.query_key_value",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h",
+    "gpt_neox.layers.6.attention.query_key_value",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h",
+    "gpt_neox.layers.4.attention.query_key_value",
+    "gpt_neox.layers.21.attention.query_key_value",
+    "gpt_neox.layers.10.attention.query_key_value",
+    "gpt_neox.layers.16.attention.query_key_value",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h",
+    "gpt_neox.layers.3.attention.query_key_value",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h",
+    "gpt_neox.layers.18.attention.dense",
+    "gpt_neox.layers.1.attention.query_key_value",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h",
+    "gpt_neox.layers.6.attention.dense",
+    "gpt_neox.layers.8.attention.query_key_value",
+    "gpt_neox.layers.23.attention.query_key_value",
+    "gpt_neox.layers.19.attention.query_key_value",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h",
+    "gpt_neox.layers.21.attention.dense",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h",
+    "gpt_neox.layers.22.attention.query_key_value",
+    "gpt_neox.layers.11.attention.query_key_value",
+    "gpt_neox.layers.14.attention.dense",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h",
+    "gpt_neox.layers.10.attention.dense",
+    "gpt_neox.layers.14.attention.query_key_value",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h",
+    "gpt_neox.layers.3.attention.dense",
+    "gpt_neox.layers.22.attention.dense",
+    "gpt_neox.layers.16.attention.dense",
+    "gpt_neox.layers.0.attention.dense",
+    "gpt_neox.layers.17.attention.query_key_value",
+    "gpt_neox.layers.19.attention.dense",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h",
+    "gpt_neox.layers.7.attention.query_key_value",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h",
+    "gpt_neox.layers.8.attention.dense",
+    "gpt_neox.layers.12.attention.query_key_value",
+    "gpt_neox.layers.9.attention.dense",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h",
+    "gpt_neox.layers.18.attention.query_key_value",
+    "gpt_neox.layers.23.attention.dense",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h",
+    "gpt_neox.layers.11.attention.dense",
+    "gpt_neox.layers.1.attention.dense",
+    "gpt_neox.layers.9.attention.query_key_value",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h",
+    "gpt_neox.layers.2.attention.dense",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h",
+    "gpt_neox.layers.13.attention.dense",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h",
+    "gpt_neox.layers.7.attention.dense",
+    "gpt_neox.layers.13.attention.query_key_value",
+    "gpt_neox.layers.17.attention.dense",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7375cb284fae9e67247dfa825494eb2e77e65731373b3bb0831380cc7698559e
+size 516778712

runs/Jul30_21-35-42_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722342946.oem-WS-C621E-SAGE-Series.2701271.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cd236551ddb0136287e80ef4c649916262faa91100344f40aca606ee3779b5
+size 5091

runs/Jul30_21-37-22_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722343044.oem-WS-C621E-SAGE-Series.2701657.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:388f61fe11426f20be4fc48c68b19ff6a464996860a1a7381f62225b70e52c39
+size 6055

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098d5fc80ff4c3f5c1282872093162d31a93a75b97e82d8d403960121db10248
+size 5240